Back to browse
Think Fu – Metacognition as a service

Think Fu – Metacognition as a service

by georgestrakhov·Mar 29, 2026·3 points·0 comments

AI Analysis

MidBig BrainNiche Gem

Prompt engineering library dressed up as metacognition infrastructure.

Strengths
  • Curates 200+ thinking moves from established creativity methodologies
  • Claude Code plugin integration makes frameworks accessible during coding
  • Addresses genuine RLHF-induced blandness in creative LLM outputs
Weaknesses
  • Landing page is nearly empty — no demo outputs or before/after comparisons
  • Essentially a prompt template collection without measurable output improvements
Category
Target Audience

Developers using Claude Code for creative tasks

Similar To

AIPRM · PromptBase · FlowGPT

Post Description

Hi HN!

I've been very unimpressed with how LLMs think when it comes to anything creative. It's no surprise - they've been lobotomized by RLHF to be helpful, predictable and consistent - all of these things are counterproductive in a more creative setting.

So I've built a little something to help LLMs be less creatively bland and dumb. It's called ThinkFu (because I believe creative thinking, when practiced well, is a martial art).

Anyway, you can watch a 3-min video demo here: https://www.youtube.com/watch?v=x-LQvX105SI

Or you can just add it to your claude code like this:

/plugin marketplace add move38studios/thinkfu

/plugin install thinkfu@move38studios-thinkfu

You can also explore what's happening in the code here: https://github.com/move38studios/thinkfu

The TL;DR is:

1. I've collected 200+ "thinking moves" from things like oblique strategies, triz, systems thinking, design thinking etc. and adapted them for LLMs

2. I've added a little randomness with variables, so that the total number of moves that you can get is somewhere around 500 billion. Because in creative thinking randomness is a feature not a bug.

3. There is a vector search and a tiny LLM router (behind an MCP) that tries to get you the right "thinking move" for whatever your problem may be.

Everything runs on cloudflare (still love you guys, despite all the recent issues).

Oh, also on first use you can opt in or out of sending the anonymized ratings back to my endpoint. The idea is that the LLM (or user) can rate whether a certain move was productive or not in a certain context.

If I collect enough ratings, I'll finetune a custom LLM for the router and I think routing will get better as a result.

Hope y'all find it interesting!

I'd be happy to answer questions and get bug reports and PR requests and what not. It's a tiny experiment - but if it works it could be fun to scale with the community.

Similar Projects

AI/ML●●Solid

I built a thinking framework for Claude

The site pairs a concrete 5-step rubric (ground facts, stress-test failures, reframe, trace implications, audit reasoning) with a blind A/B UI so humans can judge if structure actually helps an LLM — neat experimental rigor that most prompt experiments skip. It’s clever and pragmatic, but the idea isn’t brand-new (it’s essentially formalized chain-of-thought prompting) and the scope is narrow (Claude-only, small sample of topics).

Big BrainNiche Gem
bengia
203mo ago
Developer Tools●●Solid

Recover bricked Claude Code sessions with "thinking blocks" error

The repo does one painful thing well: it inspects SESSION_ID.jsonl, pinpoints where streaming/interleaving corrupted 'thinking' blocks, and offers diagnose, fix (with auto-backup), and nuke fallbacks. It's pragmatic and ruthless — small CLI commands, clear recovery workflow, and rescue-first guidance — but it's narrowly targeted to Claude Code users and won't matter to most people.

Niche GemSolve My Problem
miteshashar
103mo ago